test_redirect

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered without help. Beyond that, the description adds real behavioral context the annotations cannot: the resolution order (published page first, then rules, hop by hop), the enumerated step outcomes, and the hop count. It does not mention error conditions or limits on hop depth, but for a read-only probe this is solid disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler: the first explains the mechanism and return shape, the second gives the motivating scenario. The most important information (what it does and what it returns) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry the return contract — and it does, naming each step type (page, redirect, gone, external, not-found, loop) and the hop count. Combined with a fully documented two-parameter schema and accurate read-only annotations, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'url' and 'site' fully documented in the schema itself, including the multisite caveat and the list_sites pointer. The description adds no URL syntax or site-handling detail beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and object ('Follow a URL the way a visitor would') and names the exact resolution behavior, so an agent can immediately tell this is a diagnostic resolver, not a redirect authoring tool like create_redirect or a listing tool like list_redirects. It also enumerates the outcome taxonomy, which pins down what the tool actually produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a clear use case ('Use it to verify a migration: every old URL should end on a page in one hop'), which is actionable guidance. It stops short of five because it names no alternative for related diagnostics (list_redirects, list_not_found) and gives no explicit when-not-to-use condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.